Task_2 - Caret&Boruta
Derendyaev
2025-01-15
Задание 1: Анализ данных с использованием пакета
caret
Для выполнения первого задания создадим набор данных, используем
пакет caret для построения графиков и анализа.
options(repos = c(CRAN = "https://cran.rstudio.com"))
# Установка и загрузка пакета CARET
install.packages("caret")## package 'caret' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\dds\AppData\Local\Temp\RtmpcjFpV6\downloaded_packageslibrary(caret)## Loading required package: ggplot2## Loading required package: latticenames(getModelInfo())## [1] "ada" "AdaBag" "AdaBoost.M1"
## [4] "adaboost" "amdai" "ANFIS"
## [7] "avNNet" "awnb" "awtan"
## [10] "bag" "bagEarth" "bagEarthGCV"
## [13] "bagFDA" "bagFDAGCV" "bam"
## [16] "bartMachine" "bayesglm" "binda"
## [19] "blackboost" "blasso" "blassoAveraged"
## [22] "bridge" "brnn" "BstLm"
## [25] "bstSm" "bstTree" "C5.0"
## [28] "C5.0Cost" "C5.0Rules" "C5.0Tree"
## [31] "cforest" "chaid" "CSimca"
## [34] "ctree" "ctree2" "cubist"
## [37] "dda" "deepboost" "DENFIS"
## [40] "dnn" "dwdLinear" "dwdPoly"
## [43] "dwdRadial" "earth" "elm"
## [46] "enet" "evtree" "extraTrees"
## [49] "fda" "FH.GBML" "FIR.DM"
## [52] "foba" "FRBCS.CHI" "FRBCS.W"
## [55] "FS.HGD" "gam" "gamboost"
## [58] "gamLoess" "gamSpline" "gaussprLinear"
## [61] "gaussprPoly" "gaussprRadial" "gbm_h2o"
## [64] "gbm" "gcvEarth" "GFS.FR.MOGUL"
## [67] "GFS.LT.RS" "GFS.THRIFT" "glm.nb"
## [70] "glm" "glmboost" "glmnet_h2o"
## [73] "glmnet" "glmStepAIC" "gpls"
## [76] "hda" "hdda" "hdrda"
## [79] "HYFIS" "icr" "J48"
## [82] "JRip" "kernelpls" "kknn"
## [85] "knn" "krlsPoly" "krlsRadial"
## [88] "lars" "lars2" "lasso"
## [91] "lda" "lda2" "leapBackward"
## [94] "leapForward" "leapSeq" "Linda"
## [97] "lm" "lmStepAIC" "LMT"
## [100] "loclda" "logicBag" "LogitBoost"
## [103] "logreg" "lssvmLinear" "lssvmPoly"
## [106] "lssvmRadial" "lvq" "M5"
## [109] "M5Rules" "manb" "mda"
## [112] "Mlda" "mlp" "mlpKerasDecay"
## [115] "mlpKerasDecayCost" "mlpKerasDropout" "mlpKerasDropoutCost"
## [118] "mlpML" "mlpSGD" "mlpWeightDecay"
## [121] "mlpWeightDecayML" "monmlp" "msaenet"
## [124] "multinom" "mxnet" "mxnetAdam"
## [127] "naive_bayes" "nb" "nbDiscrete"
## [130] "nbSearch" "neuralnet" "nnet"
## [133] "nnls" "nodeHarvest" "null"
## [136] "OneR" "ordinalNet" "ordinalRF"
## [139] "ORFlog" "ORFpls" "ORFridge"
## [142] "ORFsvm" "ownn" "pam"
## [145] "parRF" "PART" "partDSA"
## [148] "pcaNNet" "pcr" "pda"
## [151] "pda2" "penalized" "PenalizedLDA"
## [154] "plr" "pls" "plsRglm"
## [157] "polr" "ppr" "pre"
## [160] "PRIM" "protoclass" "qda"
## [163] "QdaCov" "qrf" "qrnn"
## [166] "randomGLM" "ranger" "rbf"
## [169] "rbfDDA" "Rborist" "rda"
## [172] "regLogistic" "relaxo" "rf"
## [175] "rFerns" "RFlda" "rfRules"
## [178] "ridge" "rlda" "rlm"
## [181] "rmda" "rocc" "rotationForest"
## [184] "rotationForestCp" "rpart" "rpart1SE"
## [187] "rpart2" "rpartCost" "rpartScore"
## [190] "rqlasso" "rqnc" "RRF"
## [193] "RRFglobal" "rrlda" "RSimca"
## [196] "rvmLinear" "rvmPoly" "rvmRadial"
## [199] "SBC" "sda" "sdwd"
## [202] "simpls" "SLAVE" "slda"
## [205] "smda" "snn" "sparseLDA"
## [208] "spikeslab" "spls" "stepLDA"
## [211] "stepQDA" "superpc" "svmBoundrangeString"
## [214] "svmExpoString" "svmLinear" "svmLinear2"
## [217] "svmLinear3" "svmLinearWeights" "svmLinearWeights2"
## [220] "svmPoly" "svmRadial" "svmRadialCost"
## [223] "svmRadialSigma" "svmRadialWeights" "svmSpectrumString"
## [226] "tan" "tanSearch" "treebag"
## [229] "vbmpRadial" "vglmAdjCat" "vglmContRatio"
## [232] "vglmCumulative" "widekernelpls" "WM"
## [235] "wsrf" "xgbDART" "xgbLinear"
## [238] "xgbTree" "xyf"Графический разведочный анализ данных с использованием функции featurePlot()
# Создание данных
x <- matrix(rnorm(50*5), ncol=5)
y <- factor(rep(c("A", "B"), 25))
# Графический разведочный анализ данных
featurePlot(x = x, y = y)
# Сохранение графиков в *.jpg файл
jpeg("feature_plot.jpg")
featurePlot(x = x, y = y)
dev.off()## png
## 2Задание 2. Использование пакета Fselector для определения важности признаков.
# Установка и загрузка пакета Fselector
install.packages("Fselector")## Warning: package 'Fselector' is not available for this version of R
##
## A version of this package for your version of R might be available elsewhere,
## see the ideas at
## https://cran.r-project.org/doc/manuals/r-patched/R-admin.html#Installing-packages## Warning: Perhaps you meant 'FSelector' ?library(FSelector)
# Загрузка данных iris
data(iris)
# Определение важности признаков
importance <- chi.squared(Species ~ ., data = iris)
print(importance)## attr_importance
## Sepal.Length 0.6288067
## Sepal.Width 0.4922162
## Petal.Length 0.9346311
## Petal.Width 0.9432359# Выбор наиболее важных признаков
selected_features <- cutoff.k(importance, 2)
print(selected_features)## [1] "Petal.Width" "Petal.Length"Выводы: На основе показателей важности признаков можно выбрать наиболее значимые для классификации.
Задание 3. Преобразование непрерывных переменных в категориальные с помощью функции discretize() из пакета arules.
# Установка и загрузка пакета arules
install.packages("arules")## package 'arules' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\dds\AppData\Local\Temp\RtmpcjFpV6\downloaded_packageslibrary(arules)## Loading required package: Matrix##
## Attaching package: 'arules'## The following objects are masked from 'package:base':
##
## abbreviate, write# Преобразование с использованием метода "interval"
iris$Sepal.Length_interval <- discretize(iris$Sepal.Length, method="interval", breaks=4)
# Преобразование с использованием метода "frequency"
iris$Sepal.Length_frequency <- discretize(iris$Sepal.Length, method="frequency", categories=4)## Warning in discretize(iris$Sepal.Length, method = "frequency", categories = 4):
## Parameter categories is deprecated. Use breaks instead! Also, the default
## method is now frequency!# Преобразование с использованием метода "cluster"
iris$Sepal.Length_cluster <- discretize(iris$Sepal.Length, method="cluster", categories=3)## Warning in discretize(iris$Sepal.Length, method = "cluster", categories = 3):
## Parameter categories is deprecated. Use breaks instead! Also, the default
## method is now frequency!# Преобразование с использованием метода "fixed"
iris$Sepal.Length_fixed <- discretize(iris$Sepal.Length, method="fixed", breaks=c(4, 5, 6, 7, 8))
# Посмотрим на преобразованные данные
head(iris)## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5.0 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosa
## Sepal.Length_interval Sepal.Length_frequency Sepal.Length_cluster
## 1 [4.3,5.2) [5.1,5.8) [4.3,5.33)
## 2 [4.3,5.2) [4.3,5.1) [4.3,5.33)
## 3 [4.3,5.2) [4.3,5.1) [4.3,5.33)
## 4 [4.3,5.2) [4.3,5.1) [4.3,5.33)
## 5 [4.3,5.2) [4.3,5.1) [4.3,5.33)
## 6 [5.2,6.1) [5.1,5.8) [5.33,6.27)
## Sepal.Length_fixed
## 1 [5,6)
## 2 [4,5)
## 3 [4,5)
## 4 [4,5)
## 5 [5,6)
## 6 [5,6)Задание 4. Использование пакета Boruta для выбора признаков для набора данных Ozone.
install.packages("Boruta")## package 'Boruta' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\dds\AppData\Local\Temp\RtmpcjFpV6\downloaded_packages# Загрузите необходимые библиотеки
library(Boruta)
library(datasets)
# Загружаем набор данных Ozone
data("airquality")
# Очищаем данные от NA
airquality_clean <- na.omit(airquality)
# Применяем Boruta для выбора признаков
set.seed(123)
boruta_result <- Boruta(Ozone ~ ., data = airquality_clean, doTrace = 2)## 1. run of importance source...## 2. run of importance source...## 3. run of importance source...## 4. run of importance source...## 5. run of importance source...## 6. run of importance source...## 7. run of importance source...## 8. run of importance source...## 9. run of importance source...## After 9 iterations, +0.41 secs:## confirmed 4 attributes: Month, Solar.R, Temp, Wind;## still have 1 attribute left.## 10. run of importance source...## 11. run of importance source...## 12. run of importance source...## 13. run of importance source...## 14. run of importance source...## 15. run of importance source...## 16. run of importance source...## 17. run of importance source...## 18. run of importance source...## 19. run of importance source...## 20. run of importance source...## 21. run of importance source...## 22. run of importance source...## 23. run of importance source...## 24. run of importance source...## 25. run of importance source...## 26. run of importance source...## 27. run of importance source...## 28. run of importance source...## 29. run of importance source...## 30. run of importance source...## 31. run of importance source...## 32. run of importance source...## 33. run of importance source...## 34. run of importance source...## 35. run of importance source...## 36. run of importance source...## 37. run of importance source...## 38. run of importance source...## 39. run of importance source...## 40. run of importance source...## 41. run of importance source...## 42. run of importance source...## 43. run of importance source...## 44. run of importance source...## 45. run of importance source...## 46. run of importance source...## 47. run of importance source...## 48. run of importance source...## 49. run of importance source...## 50. run of importance source...## 51. run of importance source...## 52. run of importance source...## 53. run of importance source...## 54. run of importance source...## 55. run of importance source...## 56. run of importance source...## 57. run of importance source...## After 57 iterations, +2.5 secs:## confirmed 1 attribute: Day;## no more attributes left.# Просмотр результата
print(boruta_result)## Boruta performed 57 iterations in 2.540513 secs.
## 5 attributes confirmed important: Day, Month, Solar.R, Temp, Wind;
## No attributes deemed unimportant.# Убираем нерелевантные признаки
selected_features <- getSelectedAttributes(boruta_result)
# Отбираем только те столбцы, которые были выбраны
airquality_selected <- airquality_clean[, c(selected_features, "Ozone")]
# Строим график boxplot для выбранных признаков
boxplot(airquality_selected, main = "Boxplot для выбранных признаков", col = "lightblue")